Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A computer-implemented method of identifying a lumen diameter of a patient's vasculature, the method comprising: receiving a data set including one or more lumen segmentations of known healthy vessel segments of a plurality of individuals; identifying, for each segment of the known healthy vessel segments, including a section of vasculature upstream of the segment and a section of vasculature downstream of the segment; extracting one or more lumen features for each segment including a lumen feature for each section of vasculature upstream of the segment and a lumen feature for each section of vasculature downstream of the segment; determining a population-based healthy lumen diameter based on the extracted lumen feature for each segment, the extracted lumen feature for each section of vasculature upstream of the segment, and the extracted lumen feature for each section of vasculature downstream of the segment; receiving a lumen segmentation of a patient's vasculature; determining a section of the patient's vasculature; and determining a patient-specific healthy lumen diameter of the section of the patient's vasculature using the determined population-based healthy lumen diameter.
This invention relates to a computer-implemented method for determining a healthy lumen diameter in a patient's vasculature by analyzing population-based data. The method addresses the challenge of accurately assessing vessel health by comparing a patient's vasculature to a reference dataset of healthy vessel segments from multiple individuals. The process begins by receiving a dataset containing lumen segmentations of known healthy vessel segments from a population. For each segment in this dataset, the method identifies adjacent upstream and downstream sections of vasculature. Lumen features, such as diameter or cross-sectional area, are extracted for each segment and its corresponding upstream and downstream sections. These features are then used to establish a population-based healthy lumen diameter, which serves as a reference model for normal vessel dimensions. When analyzing a patient's vasculature, the method receives a lumen segmentation of the patient's vessels and identifies a specific section of interest. Using the pre-determined population-based healthy lumen diameter, the method calculates a patient-specific healthy lumen diameter for that section. This allows for personalized comparisons between the patient's vessel dimensions and the expected healthy range, aiding in diagnostic assessments. The approach leverages statistical analysis of population data to improve the accuracy of vessel health evaluations.
2. The method of claim 1 , further comprising: calculating a lumen narrowing score using the determined healthy lumen diameter, wherein the lumen narrowing score is a ratio comprising a radius of the section of the patient's vasculature to a corresponding theoretical healthy radius based on the known healthy vessel segments of the plurality of individuals.
This invention relates to medical imaging and vascular health assessment, specifically a method for evaluating lumen narrowing in a patient's vasculature by comparing it to a reference model derived from healthy individuals. The method involves analyzing a section of a patient's vasculature to determine its current lumen diameter, then calculating a lumen narrowing score that quantifies the degree of narrowing compared to a theoretical healthy state. The healthy reference is based on known healthy vessel segments from a plurality of individuals, allowing for a personalized comparison. The lumen narrowing score is derived as a ratio of the patient's vessel radius to the corresponding healthy radius from the reference model. This approach enables objective assessment of vascular health by contextualizing the patient's measurements against a statistically validated baseline, aiding in early detection of conditions like atherosclerosis or stenosis. The method may be integrated into imaging systems such as angiography or intravascular ultrasound to provide quantitative insights into vessel patency and disease progression. By leveraging population-based healthy vessel data, the technique improves diagnostic accuracy and consistency in clinical evaluations.
3. The method of claim 1 , wherein the one or more lumen features include average maximum and minimum lumen area, volume, and length.
This invention relates to medical imaging and analysis, specifically for evaluating vascular structures such as blood vessels. The technology addresses the challenge of accurately quantifying lumen features in medical imaging to assess vascular health, diagnose conditions like atherosclerosis, or plan interventions. The method involves analyzing one or more lumen features, including average maximum and minimum lumen area, volume, and length. These measurements provide detailed insights into the geometry and condition of the vessel lumen, enabling clinicians to track disease progression, evaluate treatment efficacy, or identify areas at risk of complications. The analysis may be performed on imaging data obtained from modalities such as computed tomography (CT), magnetic resonance imaging (MRI), or ultrasound. By quantifying these specific lumen parameters, the invention enhances diagnostic accuracy and supports personalized treatment decisions. The method may be integrated into imaging software or medical devices to automate lumen analysis, reducing manual effort and improving reproducibility. This approach is particularly valuable in cardiovascular applications, where precise lumen measurements are critical for assessing stenosis severity, planning stent placement, or monitoring vascular interventions. The invention improves upon existing techniques by providing a standardized, comprehensive set of lumen metrics that can be consistently applied across different imaging modalities and clinical scenarios.
4. The method of claim 1 , further comprising: splitting each of the lumen segmentations of the known healthy vessel segments into sub-units, where one unit of the sub-units corresponds to the determined section of the patient's vasculature.
This invention relates to medical imaging and vascular analysis, specifically improving the accuracy of vessel segmentation in medical images by leveraging known healthy vessel segments. The problem addressed is the difficulty in accurately segmenting vessels in patient images, particularly when the vessel structure is partially occluded or degraded. The solution involves using pre-existing segmentation data from healthy vessels to enhance the segmentation process for a patient's vasculature. The method begins by obtaining a medical image of a patient's vasculature and identifying known healthy vessel segments from a reference dataset. These healthy segments are then segmented into smaller sub-units, where each sub-unit corresponds to a specific section of the patient's vasculature. By aligning these sub-units with the patient's vessel structure, the segmentation process becomes more precise, reducing errors caused by occlusions or poor image quality. This approach ensures that the segmentation reflects the patient's actual vessel structure while incorporating the reliability of pre-segmented healthy vessel data. The technique is particularly useful in applications like angiography, where accurate vessel mapping is critical for diagnosis and treatment planning.
5. The method of claim 4 , further comprising: extracting one or more lumen features for each of the sub-units; and generating a regression to determine the healthy lumen diameter of the section of the patient's vasculature.
This invention relates to medical imaging and vascular analysis, specifically for assessing the health of a patient's vasculature. The method involves analyzing a section of a patient's vasculature to determine the healthy lumen diameter, which is useful for diagnosing conditions like atherosclerosis or other vascular diseases. The process begins by segmenting the vasculature into multiple sub-units, each representing distinct sections of the vessel. For each sub-unit, one or more lumen features are extracted, such as diameter measurements, cross-sectional area, or other geometric properties. These features are then used to generate a regression model that predicts the healthy lumen diameter for the section of the vasculature. The regression model accounts for variations in vessel structure and helps identify deviations from normal, healthy dimensions, which may indicate disease. This approach improves diagnostic accuracy by providing a quantitative assessment of vascular health based on objective measurements rather than subjective visual inspection. The method can be applied to various imaging modalities, including CT angiography, MRI, or ultrasound, to enhance the detection and monitoring of vascular conditions.
6. The method of claim 4 , wherein a segment of the known healthy vessel segments corresponds to the determined section corresponding to the identified section of the patient's vasculature.
This invention relates to medical imaging and vascular analysis, specifically improving the accuracy of vascular health assessments by comparing patient vasculature to known healthy vessel segments. The problem addressed is the difficulty in accurately diagnosing vascular conditions due to variations in vessel morphology and the lack of standardized healthy references. The solution involves selecting a segment from a database of known healthy vessel segments that closely matches a specific section of a patient's vasculature. This matching process ensures that comparisons are made against anatomically and functionally similar healthy references, improving diagnostic reliability. The method includes identifying a section of the patient's vasculature, determining a corresponding section in the database, and selecting a matching healthy vessel segment for comparison. This approach enhances the detection of abnormalities by providing a more precise and relevant reference, reducing false positives and improving treatment planning. The invention is particularly useful in applications requiring detailed vascular analysis, such as stroke prevention, peripheral artery disease assessment, and aneurysm detection. By leveraging pre-characterized healthy vessel data, the method ensures consistent and accurate evaluations across different patients and imaging modalities.
7. The method of claim 1 , further comprising: generating an estimate of fractional flow reserve, generating an estimate or sensitivity of a fractional flow reserve estimate, or generating a model based on the determined healthy lumen diameter.
This invention relates to cardiovascular diagnostics, specifically improving the assessment of coronary artery disease using fractional flow reserve (FFR) estimates. The method addresses the challenge of accurately determining FFR, a key metric for evaluating the severity of coronary artery stenosis, without invasive procedures. The invention involves analyzing medical imaging data, such as computed tomography (CT) scans, to determine the healthy lumen diameter of a coronary artery. This diameter is used to generate an FFR estimate, assess the sensitivity of that estimate, or develop a predictive model. The healthy lumen diameter is derived by comparing the current lumen diameter to a reference diameter, which may be based on anatomical landmarks, patient-specific data, or population-based norms. The method may also incorporate physiological parameters like blood pressure and heart rate to refine the FFR estimate. By providing non-invasive FFR assessments, the invention aims to enhance diagnostic accuracy and reduce the need for invasive catheterization procedures. The generated FFR estimates or sensitivity analyses can guide clinical decision-making, while the predictive models enable personalized risk stratification. This approach leverages advanced imaging and computational techniques to improve coronary artery disease evaluation.
8. The method of claim 1 , wherein the known healthy vessel segments are determined based on manual annotations.
This invention relates to medical imaging analysis, specifically for identifying healthy vessel segments in vascular imaging data. The problem addressed is the need for accurate and reliable detection of healthy vessel regions to assist in medical diagnosis and treatment planning. The method involves analyzing vascular imaging data, such as from angiography or ultrasound, to identify vessel segments that are free from disease or abnormalities. A key aspect is the determination of known healthy vessel segments, which is done through manual annotations by medical professionals. These annotations serve as ground truth data to train or validate automated detection algorithms. The method may also include preprocessing steps to enhance image quality, segmentation techniques to isolate vessel structures, and classification algorithms to distinguish healthy from diseased segments. The manual annotations ensure high accuracy in identifying healthy regions, which is critical for applications like disease progression monitoring, treatment efficacy assessment, and personalized medicine. The invention improves upon existing techniques by incorporating expert-labeled data to refine automated analysis, reducing false positives and improving diagnostic confidence.
9. A system for identifying a lumen diameter of a patient's vasculature, the system comprising: a processor configured to perform a method including: receiving a data set including one or more lumen segmentations of known healthy vessel segments of a plurality of individuals; identifying, for each segment of the known healthy vessel segments, a section of vasculature upstream of the segment and a section of vasculature downstream of the segment; extracting one or more lumen features for each segment including a lumen feature for each section of vasculature upstream of the segment and a lumen feature for each section of vasculature downstream of the segment; determining a population-based healthy lumen diameter based on the extracted lumen feature for each segment, the extracted lumen feature for each section of vasculature upstream of the segment, and the extracted lumen feature for each section of vasculature downstream of the segment; receiving a lumen segmentation of a patient's vasculature; determining a section of the patient's vasculature; and determining a patient-specific healthy lumen diameter of the section of the patient's vasculature using the determined population-based healthy lumen diameter.
The system identifies the healthy lumen diameter of a patient's vasculature by analyzing data from multiple individuals. It processes a dataset containing lumen segmentations of known healthy vessel segments from a population. For each healthy segment, the system identifies upstream and downstream sections of vasculature and extracts lumen features from these sections. These features, along with the segment's own lumen features, are used to determine a population-based healthy lumen diameter for each segment. When analyzing a patient's vasculature, the system receives a lumen segmentation of the patient's vessels, identifies a specific section of interest, and calculates a patient-specific healthy lumen diameter for that section based on the population-derived data. This approach helps assess whether a patient's vessel diameter deviates from expected healthy values, aiding in medical diagnosis and treatment planning. The system leverages both local and contextual vessel features to improve accuracy in determining healthy lumen diameters.
10. The system of claim 9 , wherein the system is further configured for: calculating a lumen narrowing score using the determined healthy lumen diameter, wherein the lumen narrowing score is a ratio comprising a radius of the section of the patient's vasculature to a corresponding theoretical healthy radius based on the known healthy vessel segments of the plurality of individuals.
This invention relates to a medical imaging system for analyzing vascular health by comparing a patient's vasculature to a database of healthy vessel segments from multiple individuals. The system determines a healthy lumen diameter for a specific section of the patient's vasculature by referencing the known healthy vessel segments, which are categorized by anatomical location, patient demographics, and other relevant factors. The system then calculates a lumen narrowing score, which quantifies the degree of stenosis or narrowing in the patient's vasculature. This score is derived as a ratio of the radius of the patient's vessel section to the corresponding theoretical healthy radius, providing a standardized metric for assessing vascular health. The system may also include features for visualizing the patient's vasculature, highlighting areas of narrowing, and generating reports for clinical decision-making. The invention aims to improve diagnostic accuracy by leveraging population-based healthy vessel data to identify deviations from normal anatomy in individual patients.
11. The system of claim 9 , wherein the one or more lumen features include average maximum and minimum lumen area, volume, and length.
This invention relates to a medical imaging system for analyzing vascular structures, such as blood vessels, to assess their condition. The system addresses the challenge of accurately quantifying vascular features to aid in diagnosing and monitoring diseases like atherosclerosis or stenosis. The system includes an imaging device, such as an intravascular ultrasound (IVUS) or optical coherence tomography (OCT) scanner, that captures cross-sectional images of a vessel. These images are processed to extract lumen features, which are the open spaces within the vessel. The system calculates key metrics from these features, including the average maximum and minimum lumen area, volume, and length. These measurements help clinicians evaluate vessel patency, identify blockages, and track disease progression. The system may also compare these metrics against reference values or historical data to provide diagnostic insights. By automating the analysis of lumen features, the system reduces manual measurement errors and improves the efficiency of vascular assessments. The invention enhances diagnostic accuracy and supports personalized treatment planning for vascular conditions.
12. The system of claim 9 , wherein the system is further configured for: splitting each of the lumen segmentations of the known healthy vessel segments into sub-units, where one unit of the sub-units corresponds to the determined section of the patient's vasculature.
This invention relates to medical imaging and vascular analysis, specifically improving the accuracy of vessel segmentation in medical imaging by leveraging known healthy vessel segments. The problem addressed is the difficulty in accurately segmenting vessels in patient imaging due to variations in vessel structure, noise, or disease, which can lead to misdiagnosis or treatment errors. The system uses pre-existing data of healthy vessel segments to enhance segmentation accuracy in patient-specific imaging. The system first identifies known healthy vessel segments from a database or prior imaging. These segments are then segmented into smaller sub-units, where each sub-unit corresponds to a specific section of the patient's vasculature. By comparing these sub-units to the patient's vessel structure, the system can refine and correct the segmentation of the patient's vessels, ensuring that the segmentation aligns with expected healthy vessel morphology. This approach improves diagnostic accuracy by reducing errors caused by abnormal or noisy vessel structures in the patient's imaging. The method is particularly useful in applications like angiography, where precise vessel segmentation is critical for diagnosing vascular diseases or planning interventions.
13. The system of claim 12 , wherein the system is further configured for: extracting one or more lumen features for each of the sub-units; and generating a regression to determine the healthy lumen diameter of the section of the patient's vasculature.
This invention relates to a medical imaging system for analyzing vasculature, specifically for determining the healthy lumen diameter of a patient's blood vessels. The system addresses the challenge of accurately assessing vessel health by quantifying lumen features and predicting the expected healthy diameter of a vessel section. The system processes medical imaging data, such as angiographic or intravascular ultrasound (IVUS) scans, to segment the vasculature into sub-units. For each sub-unit, the system extracts lumen features, which may include geometric measurements, texture characteristics, or other relevant vascular properties. These features are then used to generate a regression model that estimates the healthy lumen diameter for the analyzed section. The regression model may incorporate machine learning techniques or statistical analysis to correlate extracted features with known healthy vessel dimensions. The system improves upon prior methods by providing a data-driven approach to assess vessel health, reducing reliance on subjective interpretation. By quantifying lumen features and applying regression analysis, the system enables more objective and reproducible evaluations of vascular conditions. This can aid in diagnosing diseases like atherosclerosis or planning interventions such as stent placement. The invention enhances diagnostic accuracy and supports personalized treatment decisions.
14. The system of claim 12 , wherein a segment of the known healthy vessel segments corresponds to the determined section of the patient's vasculature.
This invention relates to medical imaging and vascular analysis, specifically a system for identifying and analyzing healthy vessel segments in a patient's vasculature. The system addresses the challenge of accurately assessing vascular health by comparing patient-specific vascular structures to a database of known healthy vessel segments. The system includes a database containing pre-labeled healthy vessel segments, a processor configured to analyze medical imaging data of a patient's vasculature, and a matching module that identifies a section of the patient's vasculature corresponding to a segment in the database. The system further includes a comparison module that evaluates differences between the patient's vessel section and the matched healthy segment, enabling detection of abnormalities such as stenosis, aneurysms, or other vascular pathologies. The matching process involves spatial and morphological alignment of the patient's vessel section with the closest matching healthy segment from the database, accounting for variations in vessel geometry and orientation. The system may also include a visualization module to display the comparison results, highlighting areas of concern for clinical evaluation. This approach improves diagnostic accuracy by leveraging a standardized reference of healthy vasculature, reducing variability in manual assessments.
15. The system of claim 9 , wherein the system is further configured for: generating an estimate of fractional flow reserve, generating an estimate or sensitivity of a fractional flow reserve estimate, or generating a model based on the determined healthy lumen diameter.
This invention relates to cardiovascular diagnostics, specifically systems for assessing coronary artery disease by estimating fractional flow reserve (FFR) and related parameters. The system determines the healthy lumen diameter of a coronary artery, which is the diameter the artery would have in the absence of disease. Using this healthy lumen diameter, the system can generate an estimate of fractional flow reserve (FFR), a measure of blood flow restriction due to stenosis. Additionally, the system can calculate the sensitivity of the FFR estimate, indicating how changes in input parameters affect the FFR value. The system may also generate a model based on the healthy lumen diameter to simulate blood flow dynamics under different conditions. This approach improves the accuracy of FFR predictions by incorporating anatomical and physiological data, reducing the need for invasive measurements. The system addresses limitations in traditional FFR estimation methods, which often rely on simplified assumptions or require invasive procedures. By leveraging the healthy lumen diameter, the system provides more reliable diagnostic insights for coronary artery disease assessment.
16. The system of claim 9 , wherein the known healthy vessel segments are determined based on manual annotations.
This invention relates to medical imaging analysis, specifically a system for identifying healthy vessel segments in vascular imaging data. The problem addressed is the need for accurate and reliable detection of healthy vessel regions to assist in medical diagnosis and treatment planning. The system processes imaging data, such as from angiography or ultrasound, to analyze vessel structures. A key feature is the determination of known healthy vessel segments, which are identified based on manual annotations provided by medical professionals. These annotations serve as ground truth data to train or validate automated detection algorithms. The system may also include preprocessing steps to enhance image quality, segmentation techniques to isolate vessel structures, and classification methods to distinguish healthy from diseased segments. The manual annotations ensure high accuracy in identifying healthy regions, which is critical for applications like early disease detection, treatment monitoring, and surgical planning. The system may integrate with existing medical imaging software or function as a standalone tool for radiologists and clinicians. The use of manual annotations ensures that the system's outputs are clinically reliable, addressing the challenge of false positives or negatives in automated vessel analysis.
17. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of identifying a lumen diameter of a patient's vasculature, the method comprising: receiving a data set including one or more lumen segmentations of known healthy vessel segments of a plurality of individuals; identifying, for each segment of the known healthy vessel segments, a section of vasculature upstream of the segment and a section of vasculature downstream of the segment; extracting one or more lumen features for each segment including a lumen feature for each section of vasculature upstream of the segment and a lumen feature for each section of vasculature downstream of the segment; determining a population-based healthy lumen diameter based on the extracted lumen feature for each segment, the extracted lumen feature for each section of vasculature upstream of the segment, and the extracted lumen feature for each section of vasculature downstream of the segment; receiving a lumen segmentation of a patient's vasculature; determining a section of the patient's vasculature; and determining a patient-specific healthy lumen diameter of the section of the patient's vasculature using the determined population-based healthy lumen diameter.
This invention relates to a method for determining a patient-specific healthy lumen diameter in a patient's vasculature by analyzing lumen segmentations from a population of healthy individuals. The method involves receiving a dataset containing lumen segmentations of known healthy vessel segments from multiple individuals. For each healthy segment, the method identifies upstream and downstream sections of vasculature and extracts lumen features from these sections. These features are used to determine a population-based healthy lumen diameter for each segment. The method then receives a lumen segmentation of a patient's vasculature, identifies a specific section of the patient's vasculature, and calculates a patient-specific healthy lumen diameter for that section using the population-based healthy lumen diameter data. This approach allows for personalized assessment of vessel health by comparing the patient's vasculature to a reference population, enabling early detection of abnormalities such as stenosis or aneurysms. The invention is implemented as computer-executable instructions stored on a non-transitory computer-readable medium, ensuring reproducibility and scalability in clinical settings.
18. The non-transitory computer readable medium of claim 17 , the method further comprising: calculating a lumen narrowing score using the determined healthy lumen diameter, wherein the lumen narrowing score is a ratio comprising a radius of the section of the patient's vasculature to a corresponding theoretical healthy radius based on the known healthy vessel segments of the plurality of individuals.
This invention relates to medical imaging and vascular health assessment, specifically a method for evaluating lumen narrowing in a patient's vasculature using comparative analysis with healthy vessel data. The system analyzes medical imaging data, such as CT scans or MRIs, to identify a section of a patient's vasculature and determine its current diameter. The method then compares this measured diameter to a theoretical healthy diameter derived from known healthy vessel segments of a plurality of individuals. A lumen narrowing score is calculated as a ratio of the patient's vessel radius to the corresponding theoretical healthy radius, providing a quantitative measure of vascular narrowing. This score helps clinicians assess the severity of stenosis or other vascular conditions by comparing the patient's vessel dimensions to a statistically derived healthy baseline. The approach standardizes vascular health assessment by leveraging population-based data, improving diagnostic accuracy and treatment planning. The invention may also include additional steps such as segmenting the vessel, correcting for imaging artifacts, and generating visual representations of the narrowing score for clinical review. The system aims to enhance early detection and monitoring of cardiovascular diseases by providing objective, data-driven insights into vessel health.
19. The non-transitory computer readable medium of claim 17 , wherein the one or more lumen features include average maximum and minimum lumen area, volume, and length.
This invention relates to medical imaging and analysis, specifically for evaluating blood vessels or other tubular structures in medical imaging data. The technology addresses the challenge of accurately quantifying lumen features, such as those in blood vessels, to assess conditions like atherosclerosis or other vascular diseases. The invention involves a computer-implemented method that processes medical imaging data to extract and analyze lumen features, including average maximum and minimum lumen area, volume, and length. These measurements are derived from segmented lumen regions within the imaging data, allowing for precise quantification of vessel characteristics. The system may also compare these features against reference values or thresholds to identify abnormalities. The invention improves upon prior methods by providing a more comprehensive set of lumen metrics, enabling better diagnosis and treatment planning. The non-transitory computer-readable medium stores instructions for performing these analyses, ensuring reproducibility and standardization in medical evaluations. This approach enhances the accuracy and reliability of vascular assessments in clinical settings.
20. The non-transitory computer readable medium of claim 17 , the method further comprising: splitting each of the lumen segmentations of the known healthy vessel segments into sub-units, where one unit of the sub-units corresponds to the determined section of the patient's vasculature.
This invention relates to medical imaging and vascular analysis, specifically improving the accuracy of vessel segmentation in medical images. The problem addressed is the difficulty in precisely identifying and analyzing healthy vessel segments in a patient's vasculature, particularly when comparing against known healthy vessel models. The solution involves a method for processing medical imaging data to enhance the segmentation and analysis of vascular structures. The method includes obtaining a medical image of a patient's vasculature and generating initial lumen segmentations for known healthy vessel segments within the image. These segmentations are then split into smaller sub-units, where each sub-unit corresponds to a specific section of the patient's vasculature. This subdivision allows for more precise matching and comparison between the patient's vessel segments and reference healthy vessel models. The process may involve further steps such as aligning the sub-units with corresponding sections of the patient's vasculature to ensure accurate analysis. The goal is to improve diagnostic accuracy by enabling detailed, localized comparisons of vessel health. The invention is implemented via a non-transitory computer-readable medium containing instructions for performing these steps, ensuring reproducibility and automation in clinical settings.
Unknown
March 3, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.